charlesfrye / cuda-substringsLinks
Because it's there.
☆16Updated 8 months ago
Alternatives and similar repositories for cuda-substrings
Users that are interested in cuda-substrings are comparing it to the libraries listed below
Sorting:
- ☆38Updated 10 months ago
- Latent Large Language Models☆18Updated 9 months ago
- Rust Implementation of micrograd☆51Updated 10 months ago
- ☆27Updated 10 months ago
- NanoGPT (124M) quality in 2.67B tokens☆28Updated 3 weeks ago
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆53Updated 3 months ago
- Using modal.com to process FineWeb-edu data☆20Updated last month
- look how they massacred my boy☆63Updated 7 months ago
- SIMD quantization kernels☆65Updated last week
- alternative way to calculating self attention☆18Updated last year
- Lego for GRPO☆28Updated last month
- A miniature version of Modal☆20Updated 11 months ago
- Simple GRPO scripts and configurations.☆58Updated 3 months ago
- utilities for loading and running text embeddings with onnx☆44Updated 9 months ago
- Chat Markup Language conversation library☆55Updated last year
- ☆19Updated 2 months ago
- [WIP] Transformer to embed Danbooru labelsets☆13Updated last year
- ☆57Updated last week
- Training code for Sparse Autoencoders on Embedding models☆38Updated 3 months ago
- PCCL (Prime Collective Communications Library) implements fault tolerant collective communications over IP☆85Updated last week
- Training hybrid models for dummies.☆21Updated 4 months ago
- NLP with Rust for Python 🦀🐍☆62Updated 2 weeks ago
- Optimizing bit-level Jaccard Index and Population Counts for large-scale quantized Vector Search via Harley-Seal CSA and Lookup Tables☆20Updated last week
- The official evaluation suite and dynamic data release for MixEval.☆11Updated 8 months ago
- Synthetic data derived by templating, few shot prompting, transformations on public domain corpora, and monte carlo tree search.☆32Updated 3 months ago
- Approximating the joint distribution of language models via MCTS☆21Updated 6 months ago
- ☆12Updated 11 months ago
- ☆48Updated last year
- Just large language models. Hackable, with as little abstraction as possible. Done for my own purposes, feel free to rip.☆44Updated last year
- j1-micro (1.7B) & j1-nano (600M) are absurdly tiny but mighty reward models.☆62Updated this week